Abstract: Disclosed herein is an anomaly detection method for link-state routing protocols, a link-state routing protocol providing for link-state update (LSU) messages to be exchanged between nodes in a packet-based network, wherein each link-state update message includes link-state advertisement (LSA) message(s) each having a respective header. The method comprises monitoring the link-state advertisement messages exchanged in the network, extracting and forming respective feature vectors with the values in the fields of the headers of the monitored link-state advertisement messages, and detecting an anomaly related to routing based on the feature vectors. In particular, detecting an anomaly related to routing includes feeding the feature vectors to a machine learning system, conveniently a one-class classifier, preferably a one-class support vector machine (OC-SVM).

Abstract: Methods, systems, and computer storage media are provided for predicting a probability of acute deterioration for a specific patient. Various discrete measurements are taken regarding the patient's current health. Those measurements are used to determine a PPOD score, which is displayed for clinicians.

Abstract: A system and method for associating Signaling System 7 logical circuits and bearer channels are presented. The system may include an event detector configured to receive an SS7 signaling message on an SS7 signaling link, parse a logical circuit from the SS7 signaling message, receive an SS7 bearer channel, and detect a bearer channel event on the SS7 bearer channel. A statistical learning model block is configured to calculate a correlation confidence value between said bearer channel and said logical circuit. The method may include parsing a logical circuit ID from a signaling message on an SS7 signal link, identifying a bearer channel associated with a bearer event on a bearer circuit, and calculating a current correlation confidence value between the logical circuit ID and the bearer channel.

Abstract: A system and method for sharing information across security boundaries including a server for sharing information between networks. The method for includes receiving data structured as semantic statements, retrieving a set of rules and ontology, processing a semantic statement from data with rules and ontology, determining whether the semantic statement is consistent with rules and ontology, and determining a fact that gives rise to an inconsistency if the semantic statement is inconsistent. The method further includes removing the fact that gives rise to the inconsistency and releasing data when the semantic statement is consistent with rules and ontology.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for anomaly detection. One of the methods includes receiving training data for updating an updateable trained first predictive model. The method includes inputting the training data into a trained second predictive model and generating predictive output data. The method includes based on the predictive output data, detecting an anomaly in the training data as compared to previously received training data. The method includes generating a retrained first predictive model based on the updateable trained first predictive model, a training function and training data that includes the received training data and previously received training data, wherein the received training data is weighted differently than the previously received training data based on the detected anomaly.

Abstract: A method of selecting and presenting content on a first system based on user preferences learned on a second system is provided. The method includes receiving a user's input for identifying items of the second content system and, in response thereto, presenting a subset of items of the second content system and receiving the user's selection actions thereof. The method includes analyzing the selected items to learn the user's content preferences for the content of the second content system and determining a relationship between the content of the first and second content systems to determine preferences relevant to items of the first content system. The method includes, in response subsequent user input for items of the first content system, selecting and ordering a collection of items of the first content system based on the user's learned content preferences determined to be relevant to the items of the first content system.

Abstract: Paralinguistic indicators are translated at a paralinguistic translation server by receiving from a source a first set of data related to a first paralinguistic indicator that is configured to enable non-verbal communications between a source and a destination. The source is one of an instant messaging system and a virtual world system and the destination is one of the textual instant messaging system and a virtual world system but differs from the source. The first set of data related to the first paralinguistic indicator is translated into a second set of data related to a second paralinguistic indicator, such that the second paralinguistic indicator that is at least partially synonymous to the non-verbal communications associated with the first paralinguistic indicator. The second set of data related to the second paralinguistic indicator is transmitted to the destination.

Abstract: Systems, methods and computer-readable media are disclosed for providing a framework for generating problem situations in a computer game. In one embodiment, the framework includes a data structure representing solution candidates, fact patterns, and a solution designator. The data structure also includes a chain of inference between the solution designator and each candidate. The computer game may generate a problem situation from the data structure and present the problem situation to a user playing the computer game.

Abstract: The present disclosure proposes implementation of a three-memristor synapse where an adjustment of synaptic strength is based on Spike-Timing-Dependent Plasticity (STDP) with dopamine signaling.

Abstract: An automatic designing system includes: a rule storage unit storing sets of rewrite rules for rewriting variable nodes of a hierarchically structured graph in a design architecture for the system; a search unit sequentially determining variable nodes as application targets for the rewrite rules by searching the graph, including components in the design architecture for the system to be designed, using a search tree; a judgment unit judging whether the rewrite rule is applicable to the determined variable node; and a rule application unit replacing the determined variable node with a partial graph, including at least one of fixed and variable nodes, according to the rewrite rule, in response to a judgment that the rewrite rule is applicable. The search unit performs the searching until an undefined variable node no longer exists in the graph to be designed, and performs backtracking on condition that no variable node is found.

Abstract: A method for interacting with a person, the method comprising: receiving a user textual input; matching a structured representation of the user textual input against expected user statement fields of knowledge database entries; wherein a knowledge database entry comprises an expected user statement field and at least one action field; wherein multiple entries of the knowledge database form a data structure that comprises multiple expected user statements fields that match an expected sequence of user textual inputs.

Abstract: A component in a graph-based computation having data processing components connected by linking elements representing data flows is updated by receiving a rule specification, generating a transform for transforming data based on the rule specification, associating the transform with a component in the graph-based computation, and in response to determining that a new rule specification has been received or an existing rule specification has been edited, updating the transform associated with the component in the graph-based computation according to the new or edited rule specification. A computation is tested by receiving a rule specification including a set of rule cases, receiving a set of test cases, each test case containing a value for one or more of the potential inputs, and for each test case, identifying one of the rule cases that will generate an output given the input values of the test case.

Abstract: A component in a graph-based computation having data processing components connected by linking elements representing data flows is updated by receiving a rule specification, generating a transform for transforming data based on the rule specification, associating the transform with a component in the graph-based computation, and in response to determining that a new rule specification has been received or an existing rule specification has been edited, updating the transform associated with the component in the graph-based computation according to the new or edited rule specification. A computation is tested by receiving a rule specification including a set of rule cases, receiving a set of test cases, each test case containing a value for one or more of the potential inputs, and for each test case, identifying one of the rule cases that will generate an output given the input values of the test case.

Abstract: A method that imputes missing values while building a predictive model. A population of solutions is created using a data set comprising missing values, wherein each solution comprises parameters of each of the predictive models and the missing values of a data set. Each of the solutions in a population is checked for fitness. After the fitness is checked, the solutions in a population are genetically evolved to establish a successive population of solutions. The process of evolving and checking fitness is continued until a stopping criterion is reached.

Abstract: A learning apparatus and method of an intelligent system according to the present invention relates to learning of an intelligent system that automatically controls a system on the basis of information about events generated in an external environment or services input by a user. In the learning, it is determined whether rules extracted from event data or service data are the same as rules already stored. Then, if it is determined that the rules are new rules, queries about the confidence of new rules are generated and provided to a user. The rules are updated on the basis of user's answers. Accordingly, it is possible to accurately grasp users' patterns by using very small amount of observation data as compared to an existing method, and to more easily sense variable patterns. Therefore, it is possible to obtain a more intelligent learning in the intelligent system.

Abstract: There are provided an identification device, an identification method and an identification processing program, which are capable of significantly reducing a processing burden. An identification device 1 can judge the magnitude relation between an occurrence probability value of a class 0 and an occurrence probability value of a class 1 from the magnitude relation between gkupper and gklower. Hence, it can be identified which one of the classes 0 and 1 is applicable to observed data D1 with a simple arithmetic processing. Accordingly, a complicated and heavy-burden arithmetic processing of an exponential function can be avoided for obtaining the occurrence probability values of the classes 0 and 1, enabling the processing burden to be significantly reduced.

Abstract: A signal processing apparatus for carrying out signal processing to convert input data into output data with a quality higher than the quality of the input data, the data processing apparatus including: a first data extraction section; a nonlinear feature quantity computation section; a processing-coefficient generation section; a second data extraction section; and a data prediction section.

Abstract: This method uses two sets of sensors to estimate certain characteristics of the movement of a device or a person or states, especially postures, they adopt. A first, abundant, set of sensors (1) is removed after a learning phase where it records with certainty the states obtained by interpreting first decisional rules. The measurements of a second set of sensors (2), much more restricted than the first, are correlated to the states reached during the learning period by second decisional rules automatically obtained by supplying a classifier. They are then interpreted to determine the new states reached by the wearer just by means of the second sensors. The results are good in spite of the low number of second sensors, thanks to the accuracy of the second decisional rules.

Abstract: Methods and apparatus for evaluating decision trees on a GPU are described. In an embodiment, the structure of a decision tree is converted into a 2D “tree” array with each row representing a node in the tree. Each row comprises details of any child nodes and the parameters which are required to perform the binary test at the node. A pixel shader can then be used to evaluate the decision tree in parallel for each input data point in an input array by navigating through rows in the 2D tree array. For each row, data is read from the input array dependent upon the parameters in the row and the shader moves to another row dependent upon the result of the binary test. On reaching a row which represents a leaf node, the pixel shader outputs evaluation results, such as a leaf node index or a probability distribution over classes.

Abstract: A method for modeling error-driven adaptive control of an aircraft. Normal aircraft plant dynamics is modeled, using an original plant description in which a controller responds to a tracking error e(k) to drive the component to a normal reference value according to an asymptote curve. Where the system senses that (1) at least one aircraft plant component is experiencing an excursion and (2) the return of this component value toward its reference value is not proceeding according to the expected controller characteristics, neural network (NN) modeling of aircraft plant operation may be changed. However, if (1) is satisfied but the error component is returning toward its reference value according to expected controller characteristics, the NN will continue to model operation of the aircraft plant according to an original description.